KIT | KIT-Bibliothek | Impressum | Datenschutz

DEAL: Deep Evidential Active Learning for Image Classification

Hemmer, Patrick; Kühl, Niklas; Schöffer, Jakob

Convolutional Neural Networks (CNNs) have proven to be state-of-the-art models for image classification. However, large labeled data sets are generally needed for the training and validation of such models. In many domains, unlabeled data is available but labeling is expensive, for instance when specific expert knowledge is required. Active Learning (AL) is one approach to mitigate the problem of limited labeled data. Through selecting the most informative and representa- tive data instances for labeling, AL can contribute to more efficient learning of a model. Recent AL methods for CNNs propose different solutions for the selection of such instances. However, they do not perform consistently well and are often computationally expensive. In this paper, we propose a novel AL algorithm that efficiently learns from unlabeled data by capturing high prediction uncertainty. By replacing the softmax standard output of a CNN with the parameters of a Dirichlet density, the model learns to identify data instances that contribute efficiently to improving model performance during training. We demonstrate in several experiments with publicly available data that our method consistently outperforms other state-of-the-art AL approaches. ... mehr

Zugehörige Institution(en) am KIT Karlsruhe Service Research Institute (KSRI)
Institut für Wirtschaftsinformatik und Marketing (IISM)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2020
Sprache Englisch
Identifikator KITopen-ID: 1000125283
Erschienen in 19th IEEE International Conference On Machine Learning And Applications, December, Miami, Florida, December 14-17, 2020
Bemerkung zur Veröffentlichung Die Veranstaltung fand wegen der Corona-Pandemie als Online-Event statt
Schlagwörter Active Learning, Convolutional Neural Networks, Deep Learning, Theory of Evidence, Uncertainty
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page